Flux LoRA Collections
Collection
Flux THE LoRA
•
130 items
•
Updated
•
32
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
prithivMLmods/Canopus-Cute-Kawaii-Flux-LoRA
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW8bit | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 25 & 2K+ |
Epoch | 17 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 70+ [ Hi-RES ]
& More ...............
Cute-kawaii, An animated image of an ice cream cone on an orange background. The ice cream in the middle of the image is white with brown dots on it. There are black eyes on the ice cream. There is a smiley face on the top of the icecream cone. The cone is made up of wicker and has ridges on the sides. The background is a vibrant orange color.
Cute-kawaii, An animated image of two brown bears on a light blue background. The bear on the left is white with brown spots on it's head and ears.while the one on the right is light brown. The bears are facing each other.with their noses pointing to the right. Both bears have black eyes and black noses.
Cute-kawaii, A vibrant red background with a triangle shaped watermelon in the center. The watermelon is in the shape of a triangle and has a smiley face on it. Below the triangle is the text "wat-a-melon" in white letters.
Parameter | Value |
---|---|
Prompt | Cute-kawaii, An animated image of two brown bears on a light blue background. The bear on the left is white with brown spots on it's head and ears.while the one on the right is light brown. The bears are facing each other.with their noses pointing to the right. Both bears have black eyes and black noses. |
Sampler | euler |
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "prithivMLmods/Canopus-Cute-Kawaii-Flux-LoRA"
trigger_word = "cute-kawaii" # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use cute-kawaii
to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev